OpenSearch Releases First Open-Source Embedding and Sparse Retrieval Models
OpenSearch has open-sourced its first dense embedding model, which beats the Qwen3 base on MTEB, alongside an asymmetric sparse retrieval model. Both English-language models are Apache 2.0 licensed and work out of the box with Sentence Transformers.
2026-11-13 ~ 2026-11-13 · 3 related posts
- OpenSearch open-sources its first dense embedding model and an asymmetric sparse retriever — tomaarsen · 2026-11-13
- OpenSearch's first 600M dense embedding model beats its Qwen3 base on MTEB — tomaarsen · 2026-11-13
- OpenSearch's new retrievers are Apache 2.0 and drop straight into Sentence Transformers — tomaarsen · 2026-11-13